This project implements the classical LeNet-5 CNN for MNIST digit classification using PyTorch. It covers a complete pipeline from data preprocessing to deployment. The model achieves ~98.8% test accuracy, showing the strong effectiveness of early CNN architectures for image classification.
convolutional-neural-networks pooling-layers stochastic-gradient-descent model-deployment learning-rate-scheduling model-generalization pytorch-deep-learning confusion-matrix-analysis real-time-inference overfitting-analysis mnist-digit-classification end-to-end-ml-pipeline lenet5-cnn feature-extraction-cnn hierarchical-feature-learning activation-functions-analysis tanh-vs-relu batch-size-generalization cnn-regularization class-wise-performance
-
Updated
Apr 27, 2026 - Jupyter Notebook